Sentiment Classification on Yelp (OOD)
93.66AccuracyFull
Evaluation results
| Method | Links | |
|---|---|---|
| FullTraining set size=1707, Backbone=RoBERTa-base2022.03 | 93.66 | |
| DynamicTraining set size=800 total, Backbone=RoBERTa2022.03 | 93.19 | |
| Static + 350 autoTraining set size=400, Backbone=RoBERTa-base2022.03 | 93.03 | |
| Static + 350 autoTraining set size=400 total, Backbone=RoBERTa2022.03 | 93.03 | |
| Dynamic-MRTraining set size=800 total, Backbone=RoBERTa2022.03 | 93.03 | |
| Dynamic-FRTraining set size=800 total, Backbone=RoBERTa2022.03 | 92.98 | |
| ALTraining set size=100 gold, Backbone=RoBERTa2022.03 | 92.47 | |
| Static + 750 autoTraining set size=800, Backbone=RoBERTa-base2022.03 | 92.36 | |
| Static + 950 autoTraining set size=1000, Backbone=RoBERTa-base2022.03 | 92.3 | |
| Static + 150 autoTraining set size=200, Backbone=RoBERTa-base2022.03 | 92.19 | |
| Static + 550 autoTraining set size=600, Backbone=RoBERTa-base2022.03 | 92.1 | |
| RRTraining set size=400, Backbone=RoBERTa-base2022.03 | 91.93 | |
| Automatics CADTraining set size=3,414 total, Backbone=RoBERTa2022.03 | 91.92 | |
| Manual CADTraining set size=3,414 gold, Backbone=RoBERTa2022.03 | 91.87 | |
| StaticTraining set size=50, Backbone=RoBERTa-base2022.03 | 91.53 | |
| StaticTraining set size=50 gold, Backbone=RoBERTa2022.03 | 91.53 | |
| Static + 1150 autoTraining set size=1200, Backbone=RoBERTa-base2022.03 | 91.47 | |
| Q-DiversityTraining Source=SST22023.05 | 90.06 | |
| DPTraining set size=400, Backbone=RoBERTa-base2022.03 | 89.6 | |
| ERMTraining Source=SST22023.05 | 89.32 | |
| EIILTraining Source=SST22023.05 | 84.05 | |
| JTTTraining Source=SST22023.05 | 80.65 |